actual-mcp-server: Command for Claude Code

.claude/commands/pr-enhance.md

pr-enhance is a command for Claude Code from agigante80/actual-mcp-server. It costs 0 tokens per session (1,251 once invoked), scanned A, original, MIT.

A tool for writing detailed pull request descriptions for the develop branch of actual-mcp-server. A pull request is a proposed change that others review before it is integrated.

In plain words
What is it for?
Use it when creating or improving a pull request, especially when it changes tools, tests, documentation, infrastructure, or the project’s core adapter.
Why use it?
It gathers the changed files, commits, and project-specific concerns so reviewers can understand the change and focus their checks.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is agigante80/actual-mcp-server's own configuration. It tells Claude Code how to work on actual-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything actual-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to agigante80/actual-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/agigante80/actual-mcp-server/main/.claude/commands/pr-enhance.md
Clone the repo
git clone --depth 1 https://github.com/agigante80/actual-mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pr-enhance

README.md
[![agentmods](https://agentmods.dev/badge/commands/agigante80/actual-mcp-server/pr-enhance/github.svg)](https://agentmods.dev/commands/agigante80/actual-mcp-server/pr-enhance)
Your own site
<a href="https://agentmods.dev/commands/agigante80/actual-mcp-server/pr-enhance"><img src="https://agentmods.dev/badge/commands/agigante80/actual-mcp-server/pr-enhance/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pr-enhance

Your own site · 80×15
<a href="https://agentmods.dev/commands/agigante80/actual-mcp-server/pr-enhance"><img src="https://agentmods.dev/badge/commands/agigante80/actual-mcp-server/pr-enhance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,251 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01251
Opus 5 $0.00000 $0.00626
Sonnet 5 $0.00000 $0.00250
Haiku 4.5 $0.00000 $0.00125

Measured 10d ago against content hash d11b21e798b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pr-enhance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/pr-enhance.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pull Request Enhancement

You are a PR optimization expert for actual-mcp-server (repo: agigante80/actual-mcp-server). Generate comprehensive PR descriptions that facilitate efficient code reviews for the develop branch workflow.

Context

The user needs to create or improve a pull request. Focus on making PRs that are easy to review, well-documented, and include all necessary context for the actual-mcp-server project.

Requirements

$ARGUMENTS

Instructions

1. PR Analysis

Gather PR context:

# Current branch and base
git branch --show-current
git log --oneline develop...HEAD

# Changed files vs develop (not main — this project targets develop)
git diff --name-status develop...HEAD

# Change statistics
git diff --shortstat develop...HEAD

# Commits
git log develop...HEAD --pretty=format:"%h %s" | head -20

Categorize changed files:

  • src/tools/*.ts → tool changes (note which tools added/modified)
  • src/lib/actual-adapter.ts → critical adapter change (requires extra scrutiny)
  • src/actualToolsManager.ts → tool registration change
  • tests/** → test changes
  • docs/**, *.md → documentation
  • docker-compose*.yaml → Docker/infra
  • package.json, tsconfig.json → config/dependency changes

2. Project-specific checks

Before writing the description, run the pre-merge validation sequence:

npm run build 2>&1 | tail -3
npm run verify-tools 2>&1 | tail -3
npm run test:unit-js 2>&1 | tail -5
npm audit --audit-level=moderate 2>&1 | tail -3

Note any failures prominently in the PR description.

3. PR Description

Generate a PR description using this template:

## Summary

[1-3 bullet points describing what this PR does and why]

## Changes

### Tools affected
[List tools added/modified, or "None — infrastructure change"]

### Files changed
- `src/tools/...` — [what changed]
- `tests/...` — [what tests added/updated]
- [other significant files]

## Type of change
- [ ] New MCP tool (requires: verify-tools count update, E2E test, docs sync)
- [ ] Bug fix (existing tool behaviour corrected)
- [ ] Enhancement (existing tool improved)
- [ ] Infrastructure / dependency update
- [ ] Documentation only

## Validation

Pre-merge checklist (run before requesting review):
- [ ] `npm run build` — TypeScript compiles cleanly
- [ ] `npm run verify-tools` — all N tools registered
- [ ] `npm run test:unit-js` — unit + schema tests pass
- [ ] `npm audit --audit-level=moderate` — no new vulnerabilities
- [ ] Amounts in integer cents (not decimal dollars) — verified
- [ ] Date fields as YYYY-MM-DD strings (not Date.now()) — verified
- [ ] withActualApi wraps every Actual API operation — verified

## Breaking changes
[None / describe any breaking changes to MCP tool contracts or env var names]

## Notes for reviewer
[Anything non-obvious: why withActualApi is used a certain way, why a certain approach was chosen, file safety tier of changed files]

Read the full file on GitHub · 152 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 152 lines · 0 tokens per session scan A d11b21e798b6

Subscribe to this mod's changes

pr-enhance is a command published in the GitHub repository agigante80/actual-mcp-server (53 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,251 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.